{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hard-aware-deeply-cascaded-embedding","title":"Hard-Aware Deeply Cascaded Embedding","arxiv_id":"1611.05720","date":"2016-11-17","proceeding":"ICCV 2017 10","authors":["Yuhui Yuan","Kuiyuan Yang","Chao Zhang"],"abstract":"Riding on the waves of deep neural networks, deep metric learning has also\nachieved promising results in various tasks using triplet network or Siamese\nnetwork. Though the basic goal of making images from the same category closer\nthan the ones from different categories is intuitive, it is hard to directly\noptimize due to the quadratic or cubic sample size. To solve the problem, hard\nexample mining which only focuses on a subset of samples that are considered\nhard is widely used. However, hard is defined relative to a model, where\ncomplex models treat most samples as easy ones and vice versa for simple\nmodels, and both are not good for training. Samples are also with different\nhard levels, it is hard to define a model with the just right complexity and\nchoose hard examples adequately. This motivates us to ensemble a set of models\nwith different complexities in cascaded manner and mine hard examples\nadaptively, a sample is judged by a series of models with increasing\ncomplexities and only updates models that consider the sample as a hard case.\nWe evaluate our method on CARS196, CUB-200-2011, Stanford Online Products,\nVehicleID and DeepFashion datasets. Our method outperforms state-of-the-art\nmethods by a large margin.","url_abs":"http://arxiv.org/abs/1611.05720v2","url_pdf":"http://arxiv.org/pdf/1611.05720v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hard-aware-deeply-cascaded-embedding","repo_url":"https://github.com/PkuRainBow/Hard-Aware-Deeply-Cascaded-Embedding_release","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-sop","task":"Image Retrieval","dataset":"SOP","model":"HDC","rank_in_archive_order":14,"of":14,"metrics":{"R@1":"69.5"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-cub-200-2011","task":"Metric Learning","dataset":"CUB-200-2011","model":"HDC","rank_in_archive_order":25,"of":30,"metrics":{"R@1":"60.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.05720","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}